扩图有时候会报错

[hjj-lmx]

Traceback (most recent call last):
File "/UD-AI-SD/stable_diffusion/server_gpu.py", line 283, in image_outpainting
outputs = brushNet_pipeline(params)
File "/UD-AI-SD/stable_diffusion/power_paint/brushNet_pipeline.py", line 25, in call
outputs = self.brushNet_pipeline(
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/UD-AI-SD/stable_diffusion/power_paint/pipeline/pipeline_PowerPaint_Brushnet_CA.py", line 1453, in call
latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
File "/usr/local/lib/python3.10/dist-packages/diffusers/schedulers/scheduling_unipc_multistep.py", line 863, in step
sample = self.multistep_uni_c_bh_update(
File "/usr/local/lib/python3.10/dist-packages/diffusers/schedulers/scheduling_unipc_multistep.py", line 776, in multistep_uni_c_bh_update
D1_t = model_t - m0
RuntimeError: The size of tensor a (170) must match the size of tensor b (142) at non-singleton dimension 3